Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2712 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7347. Min Range: -1.7347
Max Act: 1.7347. Min Act: -0.1596
Data Index: 28535 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7347. Min Range: -1.7347
Max Act: 1.7087. Min Act: -0.1612
Data Index: 7486595 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7347. Min Range: -1.7347
Max Act: 1.7173. Min Act: -0.1694
Data Index: 6577403 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7347. Min Range: -1.7347
Max Act: 1.7087. Min Act: -0.1664
Data Index: 1950345 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7347. Min Range: -1.7347
Max Act: 1.7087. Min Act: -0.1542
Data Index: 7760065 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7347. Min Range: -1.7347
Max Act: 1.7087. Min Act: -0.1699
Data Index: 7893684 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7347. Min Range: -1.7347
Max Act: 1.7000. Min Act: -0.1697
Data Index: 8558945 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7347. Min Range: -1.7347
Max Act: 1.7000. Min Act: -0.1672
Data Index: 394389 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7347. Min Range: -1.7347
Max Act: 1.7000. Min Act: -0.1694
Data Index: 1752470 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7347. Min Range: -1.7347
Max Act: 1.6827. Min Act: -0.1682
Data Index: 4767820 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7347. Min Range: -1.7347
Max Act: 1.6827. Min Act: -0.1578
Data Index: 3473694 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7347. Min Range: -1.7347
Max Act: 1.6827. Min Act: -0.1545
Data Index: 6696740 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7347. Min Range: -1.7347
Max Act: 1.6827. Min Act: -0.1494
Data Index: 8052830 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7347. Min Range: -1.7347
Max Act: 1.6913. Min Act: -0.1596
Data Index: 6226239 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7347. Min Range: -1.7347
Max Act: 1.6653. Min Act: -0.1686
Data Index: 3828355 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7347. Min Range: -1.7347
Max Act: 1.6653. Min Act: -0.1636
Data Index: 5033657 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7347. Min Range: -1.7347
Max Act: 1.6740. Min Act: -0.1694
Data Index: 3023515 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7347. Min Range: -1.7347
Max Act: 1.6653. Min Act: -0.1670
Data Index: 3844616 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7347. Min Range: -1.7347
Max Act: 1.6740. Min Act: -0.1664
Data Index: 75389 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7347. Min Range: -1.7347
Max Act: 1.6653. Min Act: -0.1696
Data Index: 1950342 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19